metadata

license: apache-2.0
base_model: biodatlab/whisper-th-small-combined
tags:
  - generated_from_trainer
datasets:
  - common_voice_17_0
metrics:
  - wer
model-index:
  - name: Whisper-small-thai
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_17_0
          type: common_voice_17_0
          config: th
          split: test
          args: th
        metrics:
          - name: Wer
            type: wer
            value: 55.432891743610334

Whisper-small-thai

This model is a fine-tuned version of biodatlab/whisper-th-small-combined on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:

Loss: 0.1073
Wer: 55.4329

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 5000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3415	0.3647	1000	0.1371	65.4958
0.1638	0.7294	2000	0.1253	60.3238
0.1995	1.0941	3000	0.1161	57.4736
0.213	1.4588	4000	0.1104	56.2358
0.2041	1.8235	5000	0.1073	55.4329

Framework versions

Transformers 4.43.3
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.19.1